Docker Prompt Generator is an open-source tool that uses a language model to generate prompts for image generation models: write an idea in plain language (including Chinese), and it produces polished prompt text for Midjourney, Stable Diffusion and similar tools. Released under the MIT license, it has about 1,200 stars on GitHub and was last updated in 2023.
Getting good results from image models depends heavily on prompt craft: the right subject description, style keywords, lighting and composition terms. This project wraps that expertise into a small Docker-deployable service. Like Midjourney’s own describe-style features, it can parse an existing image into a prompt and extend or vary a prompt you already have, so you can iterate on a visual idea instead of starting from a blank box. It is deliberately tiny (the author describes the core as a few dozen lines built on a model API) and runs comfortably in a Docker container based on common deep learning images, with CPU-only play also documented. For Chinese-speaking creators in particular, writing a sentence in Chinese and receiving an English prompt tuned for image models removes a real barrier to AI art tools.
Docker Prompt Generator is free and open source under the MIT license. You run it in your own Docker environment; the only cost is the model API usage your prompt generation consumes.
Docker Prompt Generator is for AI artists and Midjourney or Stable Diffusion users who struggle with prompt writing, especially creators who think in Chinese and want quality English prompts without manual translation and tuning.